Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    matcher
    -0.08
    <AM
    -0.08
    AVAILABLE
    -0.08
    磏
    -0.07
     sparkling
    -0.07
    不断创新
    -0.07
    色々
    -0.07
     cửa
    -0.07
    <<(
    -0.07
     chăm
    -0.06
    POSITIVE LOGITS
    .label
    0.08
     fulfillment
    0.07
     María
    0.07
    ”,
    0.07
    osition
    0.07
     Artem
    0.07
    awn
    0.07
     qualidade
    0.07
    .io
    0.07
     Fetish
    0.07
    Act Density 0.045%

    No Known Activations